TaoBaoApi 0.0.5 → 0.0.6
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +11 -5
- data/TaoBaoApi.gemspec +3 -0
- data/lib/TaoBaoApi.rb +57 -15
- data/lib/TaoBaoApi/version.rb +1 -1
- data/test.rb +9 -4
- metadata +34 -2
data/README.md
CHANGED
@@ -3,7 +3,10 @@
|
|
3
3
|
通过淘宝或天猫商品链接获取商品信息,商品信息包括标题、价格、图片。
|
4
4
|
|
5
5
|
## 环境说明
|
6
|
-
ruby 1.9.3 2.0.0
|
6
|
+
当前版本0.0.6 ruby 1.9.3 2.0.0未测试,nokogiri版本可能会有些问题
|
7
|
+
|
8
|
+
## 依赖库
|
9
|
+
nokogiri, faraday, faraday_middleware
|
7
10
|
|
8
11
|
## 安装方法
|
9
12
|
|
@@ -25,11 +28,14 @@ ruby 1.9.3 2.0.0未测试,可能会有问题
|
|
25
28
|
|
26
29
|
require 'TaoBaoApi'
|
27
30
|
|
28
|
-
good = TaoBaoApi::Good.new
|
31
|
+
good = TaoBaoApi::Good.new 'http://item.taobao.com/item.htm?id=16434110195'
|
29
32
|
|
30
|
-
info = good.get_info
|
33
|
+
info = good.get_info
|
31
34
|
|
32
|
-
p info #hash format,{:title => xxx, :price => xxx, :
|
35
|
+
p info #hash format,{:title => xxx, :price => xxx, :images => [], :url => url}
|
33
36
|
|
34
37
|
```
|
35
|
-
测试文件见test.rb
|
38
|
+
测试文件见test.rb
|
39
|
+
|
40
|
+
## Todo
|
41
|
+
* 获取促销价
|
data/TaoBaoApi.gemspec
CHANGED
data/lib/TaoBaoApi.rb
CHANGED
@@ -1,28 +1,53 @@
|
|
1
1
|
require "TaoBaoApi/version"
|
2
|
-
require 'nokogiri'
|
3
|
-
require '
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'faraday'
|
4
|
+
# require 'faraday-cookie_jar'
|
5
|
+
require 'faraday_middleware'
|
4
6
|
|
5
7
|
module TaoBaoApi
|
8
|
+
|
6
9
|
class Good
|
7
|
-
def
|
8
|
-
|
10
|
+
def initialize(url)
|
11
|
+
@url = url_filter(url)
|
12
|
+
|
13
|
+
if @url.include? 'tmall'
|
14
|
+
init_url = 'http://www.tmall.com'
|
15
|
+
else
|
16
|
+
init_url = 'http://www.taobao.com/'
|
17
|
+
end
|
18
|
+
|
19
|
+
@conn = Faraday.new(:url => init_url) do |f|
|
20
|
+
f.use FaradayMiddleware::FollowRedirects , limit: 10
|
21
|
+
|
22
|
+
f.request :url_encoded
|
23
|
+
f.adapter :net_http
|
24
|
+
f.headers[:referer] = init_url
|
25
|
+
f.headers[:user_agent] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:26.0) Gecko/20100101 Firefox/26.0'
|
26
|
+
# f.response :logger
|
27
|
+
# f.use :cookie_jar
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def get_info
|
32
|
+
return 'good_url_nil' if @url.nil?
|
9
33
|
|
10
|
-
|
11
|
-
|
34
|
+
response = @conn.get @url
|
35
|
+
|
36
|
+
doc = Nokogiri::HTML(response.body)
|
12
37
|
doc.encoding = 'utf-8'
|
13
|
-
|
38
|
+
|
14
39
|
begin
|
15
|
-
title = doc.css('title').first.text
|
40
|
+
title = title_filter(doc.css('title').first.text)
|
16
41
|
rescue NoMethodError
|
17
42
|
return 'good_not_exists'
|
18
43
|
end
|
19
44
|
|
20
45
|
images = []
|
21
|
-
if url.include? 'taobao'
|
22
|
-
price = doc.css('em.tb-rmb-num').first.text
|
46
|
+
if @url.include? 'taobao'
|
47
|
+
price = price_filter(doc.css('em.tb-rmb-num').first.text)
|
23
48
|
img_src = 'data-src'
|
24
|
-
elsif url.include? 'tmall'
|
25
|
-
price = doc.css('.J_originalPrice').first.text.strip
|
49
|
+
elsif @url.include? 'tmall'
|
50
|
+
price = price_filter(doc.css('.J_originalPrice').first.text.strip)
|
26
51
|
img_src = 'src'
|
27
52
|
else
|
28
53
|
return 'good_url_is_not_taobao'
|
@@ -36,12 +61,19 @@ module TaoBaoApi
|
|
36
61
|
{:title => title,
|
37
62
|
:price => price,
|
38
63
|
:images => images,
|
39
|
-
:url => url}
|
64
|
+
:url => @url}
|
40
65
|
end
|
41
66
|
|
42
67
|
private
|
43
|
-
|
44
|
-
|
68
|
+
#小图转大图链接
|
69
|
+
def image_filter(img_url)
|
70
|
+
img_url = "#{img_url.split('.jpg').first}.jpg"
|
71
|
+
|
72
|
+
if img_url.include? '60x60'
|
73
|
+
img_url = img_url.gsub('60x60','460x460')
|
74
|
+
end
|
75
|
+
|
76
|
+
img_url
|
45
77
|
end
|
46
78
|
|
47
79
|
def url_filter(url)
|
@@ -53,5 +85,15 @@ module TaoBaoApi
|
|
53
85
|
end
|
54
86
|
end
|
55
87
|
|
88
|
+
#去除标题空格
|
89
|
+
def title_filter(title)
|
90
|
+
title = title.split('-').first.strip.gsub(' ','') if !title.nil?
|
91
|
+
end
|
92
|
+
|
93
|
+
#格式化16.0 - 18.0 类似这样的价格区间
|
94
|
+
def price_filter price
|
95
|
+
price = price.split('-').first.strip if !price.nil? && price.include?('-')
|
96
|
+
end
|
97
|
+
|
56
98
|
end
|
57
99
|
end
|
data/lib/TaoBaoApi/version.rb
CHANGED
data/test.rb
CHANGED
@@ -1,8 +1,13 @@
|
|
1
1
|
require File.join(File.dirname(__FILE__), 'lib', 'TaoBaoApi')
|
2
2
|
|
3
|
-
|
3
|
+
url = 'http://item.taobao.com/item.htm?id=16434110195'
|
4
|
+
# url = 'http://detail.tmall.com/item.htm?id=35513218520'
|
5
|
+
# url = 'http://item.taobao.com/item.htm?spm=a1z09.5.0.0.x2gUPA&id=16718391999'
|
6
|
+
# url = 'http://item.taobao.com/item.htm?id=20132398689'
|
7
|
+
# url ='http://detail.tmall.com/item.htm?id=9153380600'
|
8
|
+
# url ='http://detail.tmall.com/item.htm?id=17350703554&spm=a1z09.5.0.0.PCBxNl'
|
9
|
+
good = TaoBaoApi::Good.new url
|
4
10
|
|
5
|
-
|
6
|
-
info = good.get_info url
|
11
|
+
info = good.get_info
|
7
12
|
|
8
|
-
p info
|
13
|
+
p info
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: TaoBaoApi
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.6
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2014-
|
12
|
+
date: 2014-02-28 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: bundler
|
@@ -59,6 +59,38 @@ dependencies:
|
|
59
59
|
- - ! '>='
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: faraday
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :runtime
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: faraday_middleware
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ! '>='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '0'
|
86
|
+
type: :runtime
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
89
|
+
none: false
|
90
|
+
requirements:
|
91
|
+
- - ! '>='
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
62
94
|
description: ! ' get goods info from taobao'
|
63
95
|
email:
|
64
96
|
- gwikimo@gmail.com
|